Update app.py

app.py

@@ -21,7 +21,7 @@ model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.float16).to
 
 model.config.sliding_window = 4096
 model.eval()
-
+model.config.use_cache = True
 # Shared stop event
 stop_event = Event()